Agentic AI Reference Architecture

Cognition · Software component

Cluster-Diverse Exemplar Selector

Software componentCognitionCognition & Memoryarc:ClusterDiverseExemplarSelector

An exemplar selector that clusters candidate questions by problem type and samples a representative from each cluster to guarantee demonstration diversity.

Responsibility. Ensures demonstration diversity through cluster-based sampling.

Also known as: Question clustering (Auto-CoT stage 1)

Variant of Exemplar Selector abstract

When to choose. Choose when demonstrations must cover diverse problem types and reasoning chains are to be generated automatically rather than written manually.

invokesspecializesalternative tosends data toalternative toText Embedding Service: invokesText Embedding ServiceExemplar Selector: specializesExemplar SelectorSimilarity Exemplar Selector: alternative toSimilarity Exemplar Sele…CoT Rationale Generator: sends data toCoT Rationale GeneratorCoreset Exemplar Pre-selector: alternative toCoreset Exemplar Pre-sel…
Direct neighbourhood (hover for relationship types)

Relationships

invokes dependency

sends data to dynamic

alternative to variability

Classification

Patterns
Automatic chain-of-thought (Auto-CoT)Cluster-based diversity samplingAuto-CoT clustering stage
Technologies
Sentence transformer models
Quality attributes
Functional suitability: correctness and validity (ISO/IEC 25010 | NIST AI RMF: valid)Reliability (ISO/IEC 25010 | NIST AI RMF: valid and reliable)
Risks mitigated
Missing important problem variants under random sampling

Sources

  1. Ch3.5: T. Nguyen, "Prompt Optimization, Few-Shot Learning, Fine-Tuning," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 3.5. ISBN: 9798244538229.
  2. Ch5.1: T. Nguyen, "Chain-of-Thought (CoT) Fundamentals," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 5.1. ISBN: 9798244538229.